Multi-task GINN-LP for Multi-target Symbolic Regression

TL;DR

This paper introduces MTRGINN-LP, an interpretable multi-task neural network for symbolic regression that captures interdependent outputs, addressing limitations of existing methods in generalization and multi-target prediction.

Contribution

It presents a novel multi-task GINN-LP model that combines shared and task-specific components for interpretable multi-target symbolic regression.

Findings

Competitive predictive performance on real-world tasks

High interpretability of the symbolic expressions

Effective modeling of inter-target dependencies

Abstract

In the area of explainable artificial intelligence, Symbolic Regression (SR) has emerged as a promising approach by discovering interpretable mathematical expressions that fit data. However, SR faces two main challenges: most methods are evaluated on scientific datasets with well-understood relationships, limiting generalization, and SR primarily targets single-output regression, whereas many real-world problems involve multi-target outputs with interdependent variables. To address these issues, we propose multi-task regression GINN-LP (MTRGINN-LP), an interpretable neural network for multi-target symbolic regression. By integrating GINN-LP with a multi-task deep learning, the model combines a shared backbone including multiple power-term approximator blocks with task-specific output layers, capturing inter-target dependencies while preserving interpretability. We validate multi-task GINN-LP on practical multi-target applications, including energy efficiency prediction and sustainable agriculture. Experimental results demonstrate competitive predictive performance alongside high interpretability, effectively extending symbolic regression to broader real-world multi-output tasks.